Office: 5723 Gates & Hillman Centers
Language Technologies Institute
I am a Professor in the Language Technologies Institute. My research focuses on Information Extraction, Text Summarization, Text Mining, Ontology Construction, Deep Reading, and related applications – all different aspects of Semantic Analysis.
Understanding the content of unstructured (free–form) text and/or of semi–structured (tables, lists, etc.) data, and converting it into internal representations that support large–scale data analytics, requires techniques for named entity recognition, entity linking, word sense disambiguation, generalization, concept fusion, and several other fundamental NLP tasks,. Creating interpretations of the canonicalized and fused results requires techniques including trend discovery, merging with information from other modalities such as images, hypothesis formation, etc. I have worked on small one–person and large multi–university projects for over 25 years, and some of the results have transitioned into government agencies (e.g., the FBI, Energy Information Administration, US Army) and corporate laboratories (e.g., IBM, GeoSemble, Google) laboratories. See case studies.